Jinhuai Liu

Surface enhanced Raman spectroscopy (SERS) is a promising sensing technique that can provide unique chemical and structural fingerprint information, but gaining reliable SERS quantitative data with high sensitivity and stability still remains a challenge. Although using a molecule as an internal standard (IS) can improve the SERS quantitative capability, the reliability and SERS measuring conditions for signal fluctuations during calibration based on IS are yet to be explored when the embedded IS molecules and target objects are located in different environments. Herein, a 3D hotspot matrix SERS platform based on Au@4-MPy@AgNPs was constructed in water with the assistance of glycerol and the dynamic signal changes from the IS, i.e. 4-Mpy, and target molecules were monitored during the process of evaporation with high sensitivity and stability. In contrast to the traditional water-dispersed drying film system, the variation trends of IS and target molecules were consistent in the glycerol-assisted liquid film protection system. Therefore, it is reasonable to calibrate the signal fluctuation by utilizing the embedded IS based on the construction strategy of a glycerol-assisted 3D hotspot platform. This work demonstrates a rational, reliable and precise SERS quantitative technique for testing analyte concentrations in practical systems and has great application prospects in the field of analytical chemistry.

Aiming at the limitation of the convolution kernel with a fixed receptive field and unknown prior to optimal network width in U-Net, multi-scale U-Net (MSU-Net) is proposed by us for medical image segmentation. First, multiple convolution sequence is used to extract more semantic features from the images. Second, the convolution kernel with different receptive fields is used to make features more diverse. The problem of unknown network width is alleviated by efficient integration of convolution kernel with different receptive fields. In addition, the multi-scale block is extended to other variants of the original U-Net to verify its universality. Five different medical image segmentation datasets are used to evaluate MSU-Net. A variety of imaging modalities are included in these datasets, such as electron microscopy, dermoscope, ultrasound, etc. Intersection over Union (IoU) of MSU-Net on each dataset are 0.771, 0.867, 0.708, 0.900, and 0.702, respectively. Experimental results show that MSU-Net achieves the best performance on different datasets. Our implementation is available athttps://github.com/CN-zdy/MSU_Net.

Multimodal medical images provide significant amounts of complementary semantic information. Therefore, multimodal medical imaging has been widely used in the segmentation of gliomas through computational neural networks. However, inputting images from different sources directly to the network does not achieve the best segmentation effect. This paper describes a convolutional neural network called F-S-Net that fuses the information from multimodal medical images and uses the semantic information contained within these images for glioma segmentation. The architecture of F-S-Net is formed by cascading two sub-networks. The first sub-network projects the multimodal medical images into the same semantic space, which ensures they have the same semantic metric. The second sub-network uses a dual encoder structure (DES) and a channel spatial attention block (CSAB) to extract more detailed information and focus on the lesion area. DES and CSAB are integrated into U-Net architectures. A multimodal glioma dataset collected by Yijishan Hospital of Wannan Medical College is used to train and evaluate the network. F-S-Net is found to achieve a dice coefficient of 0.9052 and Jaccard similarity of 0.8280, outperforming several previous segmentation methods.